Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing key arguments or main ideas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    χρι
    -0.62
     incertidumbre
    -0.57
    δί
    -0.53
    idoscope
    -0.53
    ViewImports
    -0.52
     retourne
    -0.52
     Vikipedi
    -0.52
    httpResponse
    -0.51
     Thri
    -0.51
    Sitemap
    -0.50
    POSITIVE LOGITS
    POINT
    0.63
    RepeatedField
    0.60
     message
    0.60
    POINTS
    0.60
     point
    0.59
     chords
    0.58
     salient
    0.56
     contextLoads
    0.55
     POINT
    0.54
    point
    0.54
    Act Density 0.026%

    No Known Activations